Qualitative Assessment of Machine Learning Classifiers for Employee Performance Prediction

Prediction refers to forecasting as a mathematical model that uses historical data to predict the future. It is an assumption derived based on the facts and figures. In any organization, the human resource function derives employee performance values through various parameters and sources annually. It creates a history of employee performance data used for prediction. In this research work, we use the employee performance attributes from the employee data set to predict their individual performance. There are numerous algorithms and tools available for prediction. However, we have chosen the most popular and frequently used algorithms for this study. This paper focuses on the most acceptable prediction on an employee’s performance by implementing various machine learning classifiers, namely SVM, KNN, decision tree, random forest, and logistic regression. As mentioned above, the classifier’s performance is evaluated based on the evaluation metrics such as precision, accuracy, F1-score, and log loss. The experimental results reveal that random forest provides higher accuracy (88%), higher F1-score (0.93), higher precision score (0.88), and lower log loss (0.33). Hence, the random forest classifier is more precise for predicting employee performance with the given data set than other classifiers.